Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to foreign entities or concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.86
     dAtA
    -0.73
    xtype
    -0.70
    /*
    -0.69
     Pratt
    -0.66
    iastes
    -0.66
    xFFFFFF
    -0.66
     Edwards
    -0.65
    tahui
    -0.65
    webElementGuid
    -0.64
    POSITIVE LOGITS
     étrangères
    0.88
    FOREIGN
    0.75
     étrangère
    0.74
     Foreign
    0.74
     extranjeros
    0.71
     FOREIGN
    0.70
     extranjera
    0.69
    Foreign
    0.68
    ness
    0.68
     dieux
    0.67
    Act Density 0.010%

    No Known Activations